Search Results for author:
Found 191 papers, 43 papers with code
Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation
In this work, we first propose a heavy-ball momentum based advantage actor-critic (\mbox{HB-A2C}) algorithm by integrating the heavy-ball momentum into the critic recursion that is parameterized by a linear function.
ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling
Generative retrieval, which has demonstrated effectiveness in text-to-text retrieval, utilizes a sequence-to-sequence model to directly generate candidate identifiers based on natural language queries.
Federated Model Heterogeneous Matryoshka Representation Learning
(2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header.
Source Echo Chamber: Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop
How and to what extent the source bias affects the neural recommendation models within feedback loop remains unknown.
Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content.
Guaranteeing Accuracy and Fairness under Fluctuating User Traffic: A Bankruptcy-Inspired Re-ranking Approach
Previous studies often show that the two sides' needs show different urgency: providers need a relatively long-term exposure demand while users want more short-term and accurate service.
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
In this paper, we propose RICE, an innovative refining scheme for reinforcement learning that incorporates explanation methods to break through the training bottlenecks.
pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learning
2) An iterative training strategy is designed to alternately train the global homogeneous small feature extractor and the local heterogeneous large model for effective global-local knowledge exchange.
VDTuner: Automated Performance Tuning for Vector Data Management Systems
However, due to the inherent characteristics of VDMS, automatic performance tuning for VDMS faces several critical challenges, which cannot be well addressed by the existing auto-tuning methods.
Practical Region-level Attack against Segment Anything Models
Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i. e., user prompt).
RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments
Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication.
GRASP: GRAph-Structured Pyramidal Whole Slide Image Representation
In this work, we present GRASP, a novel graph-structured multi-magnification framework for processing WSIs in digital pathology.
pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning
It assigns a shared homogeneous small feature extractor and a local gating network for each client's local heterogeneous large model.
Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective
These agents, known as LLM-based Agent, offer the potential to enhance the anthropomorphism lacking in ABM.
Distributed Data-driven Unknown-input Observers
Moving to a data-driven approach, it is shown that the input/output/state trajectories of the system are compatible with the equations of a D-DUIO, and this allows, under suitable assumptions, to express the matrices of a possible DUIO in terms of the matrices of pre-collected data.
DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
Specifically, we propose a plug-in reparameterized dynamic unit (RDU) to promote the performance and inference cost trade-off.
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning
Existing MHPFL approaches often rely on a public dataset with the same nature as the learning task, or incur high computation and communication costs.
On a Foundation Model for Operating Systems
This paper lays down the research agenda for a domain-specific foundation model for operating systems (OSes).
Robust Control of Unknown Switched Linear Systems from Noisy Data
This paper investigates the problem of data-driven stabilization for linear discrete-time switched systems with unknown switching dynamics.
Data-driven Control Against False Data Injection Attacks
To this end, a general FDI attack model is presented, which imposes minimally constraints on the switching frequency of attack channels and the magnitude of attack matrices.
pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing
To allow each data owner (a. k. a., FL clients) to train a heterogeneous and personalized local model based on its local data distribution, system resources and requirements on model structure, the field of model-heterogeneous personalized federated learning (MHPFL) has emerged.
Neural Retrievers are Biased Towards LLM-Generated Content
Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher.
pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized data.
Self-triggered Consensus Control of Multi-agent Systems from Data
In the presence of external disturbances, a model-based STC scheme is put forth for $\mathcal{H}_{\infty}$-consensus of MASs, serving as a baseline for the data-driven STC.
ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking
To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa.
STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning
The performance of these algorithms heavily relies on the sequence modeling and generation capabilities of the world model.
Ranked #5 on
Atari Games 100k
on Atari 100k
Robust Sensor Fusion for Indoor Wireless Localization
The range between two mobile nodes is fixed as priori.
A Covariance Adaptive Student's t Based Kalman Filter
This brief optimizes TKF by using the Gaussian mixture model(GMM), which generates a reasonable covariance matrix from the measurement noise to replace the one used in the existing algorithm and breaks the adjustment limit of the confidence level.
Interactive Model Fusion-Based GM-PHD Filter
In multi-target tracking (MTT), non-Gaussian measurement noise from sensors can diminish the performance of the Gaussian-assumed Gaussian mixture probability hypothesis density (GM-PHD) filter.
Quaternion MLP Neural Networks Based on the Maximum Correntropy Criterion
We propose a gradient ascent algorithm for quaternion multilayer perceptron (MLP) networks based on the cost function of the maximum correntropy criterion (MCC).
Variational Bayesian Approximations Kalman Filter Based on Threshold Judgment
The estimation of non-Gaussian measurement noise models is a significant challenge across various fields.
Unified Single-Stage Transformer Network for Efficient RGB-T Tracking
With this structure, the network can extract fusion features of the template and search region under the mutual interaction of modalities.
Ranked #4 on
Rgb-T Tracking
on GTOT
Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL
Discrete reinforcement learning (RL) algorithms have demonstrated exceptional performance in solving sequential decision tasks with discrete action spaces, such as Atari games.
Data-driven Polytopic Output Synchronization of Heterogeneous Multi-agent Systems from Noisy Data
This method utilizes measured data and a noise-matrix polytope to ensure near-optimal output synchronization.
Distributed fusion filter over lossy wireless sensor networks with the presence of non-Gaussian noise
In this paper, a generalized packet drop model is proposed to describe the packet loss phenomenon caused by DoS attacks and other factors.
Evidential Detection and Tracking Collaboration: New Problem, Benchmark and Algorithm for Robust Anti-UAV System
Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i. e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance).
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces.
A Model Fusion Distributed Kalman Filter For Non-Gaussian Observation Noise
A DKF, called model fusion DKF (MFDKF) is proposed against the non-Gaussain noise.
LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide Image Screening
We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features.
JEPOO: Highly Accurate Joint Estimation of Pitch, Onset and Offset for Music Information Retrieval
In this paper, we propose a highly accurate method for joint estimation of pitch, onset and offset, named JEPOO.
Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning
The complex relationships between operations and machines are represented precisely and concisely, for which a dual-attention network (DAN) comprising several interconnected operation message attention blocks and machine message attention blocks is proposed.
Learning Robust Data-based LQG Controllers from Noisy Data
In this work, a data-based formulation for computing the steady-state Kalman gain is proposed based on semi-definite programming (SDP) using some noise-free input-state-output data.
FedGH: Heterogeneous Federated Learning with Generalized Global Header
It is a communication and computation-efficient model-heterogeneous FL framework which trains a shared generalized global prediction header with representations extracted by heterogeneous extractors for clients' models at the FL server.
P-MMF: Provider Max-min Fairness Re-ranking in Recommender System
In this paper, we proposed an online re-ranking model named Provider Max-min Fairness Re-ranking (P-MMF) to tackle the problem.
Robust consensus control of second-order uncertain multiagent systems with velocity and input constraints (extended version)
In this paper, we investigate the consensus problem of second-order multiagent systems under directed graphs.
EdgeYOLO: An Edge-Real-Time Object Detector
This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms.
Self-triggered Resilient Stabilization of Linear Systems with Quantized Output
If, in addition, the transmission protocols at the controller-to-actuator (C-A) and sensor-to-controller (S-C) channels can be adapted, the self-triggered control architecture can be considerably simplified, leveraging a delicate observer-based deadbeat controller to eliminate the need for running the controller in parallel at the encoder side.
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
In more detail, penultimate layer outputs on the training set are considered as the representations of in-distribution (ID) data.
Ranked #11 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Minimum Error Entropy Rauch-Tung-Striebel Smoother
Outliers and impulsive disturbances often cause heavy-tailed distributions in practical applications, and these will degrade the performance of Gaussian approximation smoothing algorithms.
State Estimation of Wireless Sensor Networks in the Presence of Data Packet Drops and Non-Gaussian Noise
Distributed Kalman filter approaches based on the maximum correntropy criterion have recently demonstrated superior state estimation performance to that of conventional distributed Kalman filters for wireless sensor networks in the presence of non-Gaussian impulsive noise.
Robust Ellipse Fitting Based on Maximum Correntropy Criterion With Variable Center
For single ellipse fitting, we formulate a non-convex optimization problem to estimate the kernel bandwidth and center and divide it into two subproblems, each estimating one parameter.
Multi-scale Attention Network for Single Image Super-Resolution
ConvNets can compete with transformers in high-level tasks by exploiting larger receptive fields.
Ranked #15 on
Image Super-Resolution
on Set14 - 4x upscaling
Learning from Students: Online Contrastive Distillation Network for General Continual Learning
The goal of General Continual Learning (GCL) is to preserve learned knowledge and learn new knowledge with constant memory from an infinite data stream where task boundaries are blurry.
Deep learning-based Crop Row Detection for Infield Navigation of Agri-Robots
The novel crop row detection algorithm was tested for crop row detection performance and the capability of visual servoing along a crop row.
Data-Driven Control of Distributed Event-Triggered Network Systems
The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems (a. k. a.
Event-triggered Consensus Control of Heterogeneous Multi-agent Systems: Model- and Data-based Analysis
This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme.
Data-driven Self-triggered Control via Trajectory Prediction
Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity.
Knowledge Distillation via the Target-aware Transformer
To this end, we propose a novel one-to-all spatial matching knowledge distillation approach.
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech
However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is inconsistent with the TTS fine-tuning that takes phonemes as input.
Boosting Black-Box Adversarial Attacks with Meta Learning
Extensive experiments demonstrate that our method can not only improve the attack success rates, but also reduces the number of queries compared to other methods.
A Spatial-Temporal Attention Multi-Graph Convolution Network for Ride-Hailing Demand Prediction Based on Periodicity with Offset
To improve the efficiency of ride-hailing service, accurate prediction of transportation demand is a fundamental challenge.
Model-Based and Data-Driven Control of Event- and Self-Triggered Discrete-Time LTI Systems
To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived.
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers
Empirically, we show that existing backdoor attacks in malware classifiers are still detectable by recent defenses such as MNTD.
Online State Estimation for Supervisor Synthesis in Discrete-Event Systems with Communication Delays and Losses
Under the introduced framework, we address the state estimation problem for supervisor synthesis of networked DESs with both communication delays and losses.
HD-cos Networks: Efficient Neural Architectures for Secure Multi-Party Computation
In this paper, we study training and inference of neural networks under the MPC setup.
Collaborative Uncertainty in Multi-Agent Trajectory Forecasting
2) The results of trajectory forecasting benchmarks demonstrate that the CU-based framework steadily helps SOTA systems improve their performances.
DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021
The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness.
Data-driven Control of Dynamic Event-triggered Systems with Delays
Data-based representations for time-invariant linear systems with known or unknown system input matrices are first developed, along with a novel class of dynamic triggering schemes for sampled-data systems with time delays.
Data-Driven Resilient Predictive Control under Denial-of-Service
Finally, a numerical example is given to validate the effectiveness of the proposed control method.
Balancing Value Underestimation and Overestimation with Realistic Actor-Critic
Model-free deep reinforcement learning (RL) has been successfully applied to challenging continuous control domains.
A New Approach for Verification of Delay Coobservability of Discrete-Event Systems
Thus, techniques for the verification of delay coobservability can be leveraged to verify delay $K$-codiagnosability.
HD-cos Networks: Efficient Neural Architechtures for Secure Multi-Party Computation
In this paper, we study training and inference of neural networks under the MPC setup.
Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation
Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items.
Generalized Minimum Error Entropy for Adaptive Filtering
In our study, a novel concept, called generalized error entropy, utilizing the generalized Gaussian density (GGD) function as the kernel function is proposed.
The 2nd Anti-UAV Workshop & Challenge: Methods and Results
The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.
Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm
Experimental results base on three publicly available benchmarks showed that in both of the implementations, Pre-Rank can respectively outperform the underlying ranking models and achieved state-of-the-art performances.
SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments
Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning.
Resonant Beam Communications with Echo Interference Elimination
Resonant beam communications (RBCom) is capable of providing wide bandwidth when using light as the carrier.
Partial Maximum Correntropy Regression for Robust Trajectory Decoding from Noisy Epidural Electrocorticographic Signals
The aim of this study is to propose a new robust implementation for PLSR.
A Logical Neural Network Structure With More Direct Mapping From Logical Relations
Therefore, in order to represent logical relations more clearly by the neural network structure and to read out logical relations from it, this paper proposes a novel logical ANN model by designing the new logical neurons and links in demand of logical representation.
SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation
Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis.
Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention
Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process.
Resilient Control under Quantization and Denial-of-Service: Co-designing a Deadbeat Controller and Transmission Protocol
When both input and output channels are subject to DoS attacks and quantization, the proposed structure is shown able to decouple the encoding schemes for input, output, and estimated output signals.
A posteriori error analysis of hybrid high-order method for the Stokes problem
We present a residual-based a posteriori error estimator for the hybrid high-order (HHO) method for the Stokes model problem.
Numerical Analysis Numerical Analysis
SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
Collaborative filtering has been largely used to advance modern recommender systems to predict user preference.
Theory of Plasma-Cascade Instability
In this paper we present theory of novel micro-bunching instability.
Plasma Physics Accelerator Physics
Human Action Recognition from Various Data Modalities: A Review
Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action.
Exciton-phonon coupling strength in single-layer MoSe2 at room temperature
Single-layer transition metal dichalcogenides are at the center of an ever increasing research effort both in terms of fundamental physics and applications.
Mesoscale and Nanoscale Physics Materials Science
Decentralized TD Tracking with Linear Function Approximation and its Finite-Time Analysis
The present contribution deals with decentralized policy evaluation in multi-agent Markov decision processes using temporal-difference (TD) methods with linear function approximation for scalability.
Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition
With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.
SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval
Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching.
PDLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Pressure and Dynamic Light Duration
Existing ineffective and inflexible traffic light control at urban intersections can often lead to congestion in traffic flows and cause numerous problems, such as long delay and waste of energy.
A Traffic Light Dynamic Control Algorithm with Deep Reinforcement Learning Based on GNN Prediction
Then, the results of traffic flow prediction are used in traffic light control, and the agent combines the predicted results with the observed current traffic conditions to dynamically control the phase and duration of the traffic lights at the intersection.
Urban Sensing based on Mobile Phone Data: Approaches, Applications and Challenges
We classify these existing methods and present a taxonomy of the related work by discussing their pros and cons.
Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data
This robust learning task entails an infinite-dimensional optimization problem, which is challenging.
Reinforcement Learning for Caching with Space-Time Popularity Dynamics
With the tremendous growth of data traffic over wired and wireless networks along with the increasing number of rich-media applications, caching is envisioned to play a critical role in next-generation networks.
Throwing Darts in the Dark? Detecting Bots with Limited Data using Neural Data Augmentation
We evaluate this idea and show our method can train a model that outperforms existing methods with only 1% of the labeled data.
Resonant Beam Communications: Principles and Designs
Wireless optical communications (WOC) has carriers up to several hundred terahertz, which offers several advantages, such as ultrawide bandwidth and no electromagnetic interference.
DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous Driving
We present a visual localization framework based on novel deep attention aware features for autonomous driving that achieves centimeter level localization accuracy.
Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness
Numerical tests using real load data on the IEEE $118$-bus benchmark system showcase the improved estimation and robustness performance of the proposed scheme compared with several state-of-the-art alternatives.
Numerical simulation of sky localization for LISA-TAIJI joint observation
The precision of sky localization could be improved by around 1 to 3 times comparing to single LISA at a given percentage of sources.
General Relativity and Quantum Cosmology Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
Scene Text Recognition With Finer Grid Rectification
Scene Text Recognition is a challenging problem because of irregular styles and various distortions.
Finite-Sample Analysis of Decentralized Temporal-Difference Learning with Linear Function Approximation
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear function approximation to handle large state spaces in practice.
Easy First Relation Extraction with Information Redundancy
Many existing relation extraction (RE) models make decisions globally using integer linear programming (ILP).
A Statistical Learning Approach to Reactive Power Control in Distribution Systems
Taking a statistical learning viewpoint, the input-output relationship between each grid state and the corresponding optimal reactive power control is parameterized in the present work by a deep neural network, whose unknown weights are learned offline by minimizing the power loss over a number of historical and simulated training pairs.
A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation
Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the underlying stochastic noise sequence.
Semantic Correlation Promoted Shape-Variant Context for Segmentation
In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region.
Ranked #13 on
Semantic Segmentation
on COCO-Stuff test
Boundary-Aware Feature Propagation for Scene Segmentation
Furthermore, we propose a boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image.
Ranked #38 on
Semantic Segmentation
on PASCAL Context
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition.
Ranked #5 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Unpaired Image Captioning via Scene Graph Alignments
Most of current image captioning models heavily rely on paired image-caption datasets.
Toward Achieving Robust Low-Level and High-Level Scene Parsing
Furthermore, we introduce a “dense skip” architecture to retain a rich set of low-level information from the pre-trained CNN, which is essential to improve the low-level parsing performance.
Deep Reinforcement Learning for Adaptive Caching in Hierarchical Content Delivery Networks
To handle the large continuous state space, a scalable deep reinforcement learning approach is pursued.
2D LiDAR Map Prediction via Estimating Motion Flow with GRU
To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing.
Skeleton-Based Online Action Prediction Using Scale Selection Network
Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step.
Ranked #68 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Feature Boosting Network For 3D Pose Estimation
Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation.
Real-time Power System State Estimation and Forecasting via Deep Neural Networks
To bypass these hurdles, this paper advocates deep neural networks (DNNs) for real-time power system monitoring.
Modeling Local Dependence in Natural Language with Multi-channel Recurrent Neural Networks
In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local semantic structure information.
Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images
As a fundamental and challenging problem in computer vision, hand pose estimation aims to estimate the hand joint locations from depth images.
Graininess-Aware Deep Feature Learning for Pedestrian Detection
In this paper, we propose a graininess-aware deep feature learning method for pedestrian detection.
Learning ReLU Networks on Linearly Separable Data: Algorithm, Optimality, and Generalization
In this context, the problem of learning a two-layer ReLU network is approached in a binary classification setting, where the data are linearly separable and a hinge loss criterion is adopted.
Early action prediction by soft regression
Our formulation of soft regression framework 1) overcomes a usual assumption in existing early action prediction systems that the progress level of on-going sequence is given in the testing stage; and 2) presents a theoretical framework to better resolve the ambiguity and uncertainty of subsequences at early performing stage.
Ranked #74 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Motion-Guided Cascaded Refinement Network for Video Object Segmentation
Then, the proposed Cascaded Refinement Network(CRN) takes the coarse segmentation as guidance to generate an accurate segmentation of full resolution.
Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation
In this paper, we first propose a novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context.
Ranked #16 on
Semantic Segmentation
on COCO-Stuff test
Person Re-Identification With Cascaded Pairwise Convolutions
In this paper, a novel deep architecture named BraidNet is proposed for person re-identification.
SSNet: Scale Selection Network for Online 3D Action Prediction
As there are significant temporal scale variations of the observed part of the ongoing action at different progress levels, we propose a novel window scale selection scheme to make our network focus on the performed part of the ongoing action and try to suppress the noise from the previous actions at each time step.
Progressive Attention Guided Recurrent Network for Salient Object Detection
In this paper, we propose a novel attention guided network which selectively integrates multi-level contextual information in a progressive manner.
Ranked #14 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
A Bi-Directional Message Passing Model for Salient Object Detection
In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection.
Ranked #2 on
RGB Salient Object Detection
on ISTD
Nonlinear Dimensionality Reduction for Discriminative Analytics of Multiple Datasets
Under certain conditions, dPCA is proved to be least-squares optimal in recovering the component vector unique to the target data relative to background data.
Canonical Correlation Analysis of Datasets with a Common Source Graph
Canonical correlation analysis (CCA) is a powerful technique for discovering whether or not hidden sources are commonly present in two (or more) datasets.
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space.
Unpaired Image Captioning by Language Pivoting
Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description.
Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation.
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
We propose a novel approach for cost-adjustable inference in CNNs - Stochastic Downsampling Point (SDPoint).
Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks
First, we learn RNN parameters to discriminate between the target object and background in the first frame of a test sequence.
Solving Most Systems of Random Quadratic Equations
For certain random measurement models, the proposed procedure returns the true solution $\bm{x}$ with high probability in time proportional to reading the data $\{(\bm{a}_i;y_i)\}_{1\le i \le m}$, provided that the number $m$ of equations is some constant $c>0$ times the number $n$ of unknowns, that is, $m\ge cn$.
Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities.
DPCA: Dimensionality Reduction for Discriminative Analytics of Multiple Large-Scale Datasets
Principal component analysis (PCA) has well-documented merits for data extraction and dimensionality reduction.
Blob Reconstruction Using Unilateral Second Order Gaussian Kernels With Application to High-ISO Long-Exposure Image Denoising
Blob detection and image denoising are fundamental, and sometimes related, tasks in computer vision.
Stack-Captioning: Coarse-to-Fine Learning for Image Captioning
On the other hand, multi-stage image caption model is hard to train due to the vanishing gradient problem.
A Novel Neural Network Model Specified for Representing Logical Relations
Inhibitory links inhibit the connected exciting links conditionally to make this neural network model represent logical relations correctly.
Numerical simulation of time delay interferometry for new LISA, TAIJI and other LISA-like missions
In this paper, we follow the same procedure to simulate the time delay interferometry numerically for the new LISA mission and the TAIJI mission together with LISA-like missions of arm length 1, 2, 4, 5 and 6 Gm.
Instrumentation and Methods for Astrophysics General Relativity and Quantum Cosmology
Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks
In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition.
Ranked #66 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
However, during inference the lower layers do not know about high layer features, although they contain contextual high semantics that benefit low layers to adaptively extract informative features for later layers.
Episodic CAMN: Contextual Attention-Based Memory Networks With Iterative Feedback for Scene Labeling
Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification.
Deep Level Sets for Salient Object Detection
Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.
Global Context-Aware Attention LSTM Networks for 3D Action Recognition
Hence we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for 3D action recognition, which is able to selectively focus on the informative joints in the action sequence with the assistance of global contextual information.
Ranked #7 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
Skeleton-based human action recognition has attracted a lot of research attention during the past few years.
Ranked #6 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Reinforcement Learning for Learning Rate Control
Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks.
Solving Almost all Systems of Random Quadratic Equations
This paper deals with finding an $n$-dimensional solution $x$ to a system of quadratic equations of the form $y_i=|\langle{a}_i, x\rangle|^2$ for $1\le i \le m$, which is also known as phase retrieval and is NP-hard in general.
Towards Monetary Incentives in Social Q&A Services
Community-based question answering (CQA) services are facing key challenges to motivate domain experts to provide timely answers.
Randomized Block Frank-Wolfe for Convergent Large-Scale Learning
To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates.
An Empirical Study of Language CNN for Image Captioning
Language Models based on recurrent neural networks have dominated recent image caption generation tasks.
Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow
This paper puts forth a novel algorithm, termed \emph{truncated generalized gradient flow} (TGGF), to solve for $\bm{x}\in\mathbb{R}^n/\mathbb{C}^n$ a system of $m$ quadratic equations $y_i=|\langle\bm{a}_i,\bm{x}\rangle|^2$, $i=1, 2,\ldots, m$, which even for $\left\{\bm{a}_i\in\mathbb{R}^n/\mathbb{C}^n\right\}_{i=1}^m$ random is known to be \emph{NP-hard} in general.
Improving Fully Convolution Network for Semantic Segmentation
In addition, dense skip connections are added so that the context network can be effectively optimized.
Sparse Phase Retrieval via Truncated Amplitude Flow
Upon formulating sparse PR as an amplitude-based nonconvex optimization task, SPARTA works iteratively in two stages: In stage one, the support of the underlying sparse signal is recovered using an analytically well-justified rule, and subsequently, a sparse orthogonality-promoting initialization is obtained via power iterations restricted on the support; and, in the second stage, the initialization is successively refined by means of hard thresholding based gradient-type iterations.
Information Theory Information Theory Optimization and Control
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers.
Solving Large-scale Systems of Random Quadratic Equations via Stochastic Truncated Amplitude Flow
A novel approach termed \emph{stochastic truncated amplitude flow} (STAF) is developed to reconstruct an unknown $n$-dimensional real-/complex-valued signal $\bm{x}$ from $m$ `phaseless' quadratic equations of the form $\psi_i=|\langle\bm{a}_i,\bm{x}\rangle|$.
Decision Making Based on Cohort Scores for Speaker Verification
In this paper, we propose a decision making approach based on multiple scores derived from a set of cohort GMMs (cohort scores).
Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images.
A Siamese Long Short-Term Memory Architecture for Human Re-Identification
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance.
Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
However, current networks extract fixed representations for each image regardless of other images which are paired with it and the comparison with other images is done only at the final level.
Ranked #120 on
Person Re-Identification
on Market-1501
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell.
Context-Aware Gaussian Fields for Non-Rigid Point Set Registration
Point set registration (PSR) is a fundamental problem in computer vision and pattern recognition, and it has been successfully applied to many applications.
Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow
This paper presents a new algorithm, termed \emph{truncated amplitude flow} (TAF), to recover an unknown vector $\bm{x}$ from a system of quadratic equations of the form $y_i=|\langle\bm{a}_i,\bm{x}\rangle|^2$, where $\bm{a}_i$'s are given random measurement vectors.
Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.
Scene Parsing with Integration of Parametric and Non-parametric Models
The local beliefs of pixels are output by CNN-Ensemble.
Recurrent Attentional Networks for Saliency Detection
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection.
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes.
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos
Single modality action recognition on RGB or depth sequences has been extensively explored recently.
Multi-task CNN Model for Attribute Prediction
Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes.
Recent Advances in Convolutional Neural Networks
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.
